Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10441
    Prev
    Next
    INDEX
    Explanations

    instances of actions or procedures being described, particularly involving the use of code or methodologies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.48
     intptr
    -0.48
    >{@
    -0.48
     Coordinate
    -0.47
    Coordinate
    -0.45
     pinulongan
    -0.42
    coordinate
    -0.41
    garek
    -0.38
    gamento
    -0.38
     coordination
    -0.37
    POSITIVE LOGITS
     compute
    1.17
     calculate
    1.12
     plot
    0.96
     convert
    0.79
     estimate
    0.77
    compute
    0.77
     construct
    0.73
    calculate
    0.71
     generate
    0.71
     project
    0.71
    Activations Density 1.232%

    No Known Activations